File size: 5,779 Bytes
6c2c0a5 f9fbbdb dee7540 f9fbbdb 6c2c0a5 39c7abf f715311 8ab80d4 b554bbb 3be9882 e632542 606c172 d00ce62 2b4f515 fc69537 615dfd5 3505f03 83c917f f9fbbdb 39c7abf dee7540 50a5cbe 6c2c0a5 0c905a5 dee7540 6c2c0a5 39c7abf 6c2c0a5 f9fbbdb 6c2c0a5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.2,
"eval_steps": 50,
"global_step": 750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"grad_norm": 0.05632242560386658,
"learning_rate": 0.00013297872340425532,
"loss": 1.8852,
"step": 50
},
{
"epoch": 0.08,
"eval_loss": 1.707169532775879,
"eval_runtime": 27.6118,
"eval_samples_per_second": 3.622,
"eval_steps_per_second": 0.471,
"step": 50
},
{
"epoch": 0.16,
"grad_norm": 0.02606302499771118,
"learning_rate": 0.0002632978723404255,
"loss": 1.6036,
"step": 100
},
{
"epoch": 0.16,
"eval_loss": 1.4855879545211792,
"eval_runtime": 27.6396,
"eval_samples_per_second": 3.618,
"eval_steps_per_second": 0.47,
"step": 100
},
{
"epoch": 0.24,
"grad_norm": 0.034023039042949677,
"learning_rate": 0.00039627659574468084,
"loss": 1.5186,
"step": 150
},
{
"epoch": 0.24,
"eval_loss": 1.466215968132019,
"eval_runtime": 27.5933,
"eval_samples_per_second": 3.624,
"eval_steps_per_second": 0.471,
"step": 150
},
{
"epoch": 0.32,
"grad_norm": 0.04070857912302017,
"learning_rate": 0.0004967397747480735,
"loss": 1.4822,
"step": 200
},
{
"epoch": 0.32,
"eval_loss": 1.4602761268615723,
"eval_runtime": 27.615,
"eval_samples_per_second": 3.621,
"eval_steps_per_second": 0.471,
"step": 200
},
{
"epoch": 0.4,
"grad_norm": 0.03537657856941223,
"learning_rate": 0.00048192056905749855,
"loss": 1.5035,
"step": 250
},
{
"epoch": 0.4,
"eval_loss": 1.4578460454940796,
"eval_runtime": 27.6799,
"eval_samples_per_second": 3.613,
"eval_steps_per_second": 0.47,
"step": 250
},
{
"epoch": 0.48,
"grad_norm": 0.040425803512334824,
"learning_rate": 0.00046710136336692356,
"loss": 1.4813,
"step": 300
},
{
"epoch": 0.48,
"eval_loss": 1.4557801485061646,
"eval_runtime": 27.6578,
"eval_samples_per_second": 3.616,
"eval_steps_per_second": 0.47,
"step": 300
},
{
"epoch": 0.56,
"grad_norm": 0.03970955312252045,
"learning_rate": 0.00045228215767634857,
"loss": 1.4878,
"step": 350
},
{
"epoch": 0.56,
"eval_loss": 1.4533815383911133,
"eval_runtime": 27.6598,
"eval_samples_per_second": 3.615,
"eval_steps_per_second": 0.47,
"step": 350
},
{
"epoch": 0.64,
"grad_norm": 0.03238854929804802,
"learning_rate": 0.0004374629519857736,
"loss": 1.4765,
"step": 400
},
{
"epoch": 0.64,
"eval_loss": 1.4522851705551147,
"eval_runtime": 27.5987,
"eval_samples_per_second": 3.623,
"eval_steps_per_second": 0.471,
"step": 400
},
{
"epoch": 0.72,
"grad_norm": 0.04000236839056015,
"learning_rate": 0.0004226437462951986,
"loss": 1.4803,
"step": 450
},
{
"epoch": 0.72,
"eval_loss": 1.4484608173370361,
"eval_runtime": 27.6359,
"eval_samples_per_second": 3.618,
"eval_steps_per_second": 0.47,
"step": 450
},
{
"epoch": 0.8,
"grad_norm": 0.035757772624492645,
"learning_rate": 0.0004078245406046236,
"loss": 1.4925,
"step": 500
},
{
"epoch": 0.8,
"eval_loss": 1.4477622509002686,
"eval_runtime": 27.6496,
"eval_samples_per_second": 3.617,
"eval_steps_per_second": 0.47,
"step": 500
},
{
"epoch": 0.88,
"grad_norm": 0.039886392652988434,
"learning_rate": 0.0003930053349140486,
"loss": 1.49,
"step": 550
},
{
"epoch": 0.88,
"eval_loss": 1.4466557502746582,
"eval_runtime": 27.6503,
"eval_samples_per_second": 3.617,
"eval_steps_per_second": 0.47,
"step": 550
},
{
"epoch": 0.96,
"grad_norm": 0.035769980400800705,
"learning_rate": 0.00037818612922347364,
"loss": 1.4888,
"step": 600
},
{
"epoch": 0.96,
"eval_loss": 1.4460580348968506,
"eval_runtime": 27.6213,
"eval_samples_per_second": 3.62,
"eval_steps_per_second": 0.471,
"step": 600
},
{
"epoch": 1.04,
"grad_norm": 0.039503153413534164,
"learning_rate": 0.00036336692353289865,
"loss": 1.4732,
"step": 650
},
{
"epoch": 1.04,
"eval_loss": 1.4470006227493286,
"eval_runtime": 27.6084,
"eval_samples_per_second": 3.622,
"eval_steps_per_second": 0.471,
"step": 650
},
{
"epoch": 1.12,
"grad_norm": 0.04102110490202904,
"learning_rate": 0.00034854771784232366,
"loss": 1.4677,
"step": 700
},
{
"epoch": 1.12,
"eval_loss": 1.4475681781768799,
"eval_runtime": 27.6032,
"eval_samples_per_second": 3.623,
"eval_steps_per_second": 0.471,
"step": 700
}
],
"logging_steps": 50,
"max_steps": 1875,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.641442504933376e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|